COVID-19 Analysis
Katie Forthman
Mon May 11 16:35:52 2020
Click here for interactive plots:
Click here to see how cities and counties overlap:
Compare COVID stats to Neighborhood Factors
data.cor <- cor(county.Demo_and_Covid.allcounties[,-1], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
Compare COVID stats to 500 cities data and Neighborhood Factors
data.cor2 <- cor(county.Demo_and_Covid.500counties[,-c(1:2)], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor2, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
corrplot.mixed(data.cor2[7:13,c(1:5, 14:42,6)], upper = 'ellipse', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
—-Linear Mixed Effects Model —-
this.lme <- lmer("total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)", data = county.Demo_and_Covid.500counties)## Warning: Some predictor variables are on very different scales: consider
## rescaling
## Warning: Some predictor variables are on very different scales: consider
## rescalingprint(summary(this.lme), correlation=TRUE)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## "total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)"
## Data: county.Demo_and_Covid.500counties
##
## REML criterion at convergence: -1196.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.9239 -0.3467 -0.0905 0.1813 5.7059
##
## Random effects:
## Groups Name Variance Std.Dev.
## stateID (Intercept) 0.000001237 0.001112
## Residual 0.000013726 0.003705
## Number of obs: 178, groups: stateID, 33
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) -0.0088728834 0.0095789526 66.4431597640
## Affluence 0.0047551818 0.0011057928 98.8186326132
## Singletons.in.Tract 0.0014636650 0.0009125870 139.7179627723
## Seniors.in.Tract 0.0009063921 0.0011971126 148.3323289807
## African.Americans.in.Tract 0.0005683633 0.0010066109 150.8215890761
## Noncitizens.in.Tract 0.0008957367 0.0007772629 126.0172194073
## High.BP 0.0001790185 0.0001891643 107.1534585888
## Binge.Drinking 0.0001313838 0.0001565644 40.0016387225
## Cancer -0.0009458260 0.0011016952 96.5465275784
## Asthma 0.0006009592 0.0005552458 38.9547625118
## Heart.Disease 0.0010436256 0.0013046790 71.1343947056
## COPD -0.0000906337 0.0010788490 73.4636711157
## Smoking -0.0000873279 0.0002272215 77.9845008855
## Diabetes -0.0005154809 0.0005350691 78.8502298269
## No.Physical.Activity -0.0000262524 0.0002049846 87.1530062200
## Obesity 0.0002431056 0.0001768796 94.5915812540
## Poor.Sleeping.Habits -0.0000184302 0.0001655746 121.6091808903
## Poor.Mental.Health -0.0000630741 0.0004139261 30.2850452692
## Testing_Rate 0.0000004972 0.0000002901 33.0683157421
## Hospitalization_Rate -0.0000918852 0.0000873027 27.1597043361
## t value Pr(>|t|)
## (Intercept) -0.926 0.3576
## Affluence 4.300 0.0000401 ***
## Singletons.in.Tract 1.604 0.1110
## Seniors.in.Tract 0.757 0.4502
## African.Americans.in.Tract 0.565 0.5732
## Noncitizens.in.Tract 1.152 0.2513
## High.BP 0.946 0.3461
## Binge.Drinking 0.839 0.4064
## Cancer -0.859 0.3927
## Asthma 1.082 0.2858
## Heart.Disease 0.800 0.4264
## COPD -0.084 0.9333
## Smoking -0.384 0.7018
## Diabetes -0.963 0.3383
## No.Physical.Activity -0.128 0.8984
## Obesity 1.374 0.1726
## Poor.Sleeping.Habits -0.111 0.9116
## Poor.Mental.Health -0.152 0.8799
## Testing_Rate 1.714 0.0959 .
## Hospitalization_Rate -1.052 0.3018
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Correlation of fixed effects could have been required in summary()##
## Correlation of Fixed Effects:
## (Intr) Afflnc Sng..T Snr..T A.A..T Nnc..T Hgh.BP Bng.Dr Cancer
## Affluence 0.134
## Sngltns.n.T 0.018 0.078
## Snrs.n.Trct 0.569 0.377 0.193
## Afrcn.Am..T 0.159 0.147 -0.410 0.139
## Nnctzns.n.T -0.004 0.105 0.045 0.067 -0.079
## High.BP -0.004 0.241 0.067 0.112 -0.096 0.398
## Bing.Drnkng -0.286 -0.199 -0.300 -0.196 0.076 0.040 0.133
## Cancer -0.590 -0.196 0.181 -0.328 -0.075 -0.141 -0.380 -0.111
## Asthma -0.369 -0.205 -0.233 -0.183 0.088 0.099 0.171 0.002 0.045
## Heart.Dises -0.148 0.075 -0.289 -0.151 0.249 -0.105 -0.015 0.060 -0.472
## COPD 0.565 0.041 0.136 0.281 -0.006 0.286 0.183 0.109 -0.270
## Smoking -0.167 0.139 -0.169 -0.102 -0.058 -0.005 -0.069 -0.297 0.086
## Diabetes 0.075 -0.339 -0.107 -0.227 -0.307 -0.329 -0.525 0.045 0.239
## N.Physcl.Ac -0.181 -0.055 0.078 -0.038 -0.036 -0.218 -0.116 0.106 0.481
## Obesity 0.006 0.431 0.422 0.305 0.144 0.200 -0.084 -0.241 0.111
## Pr.Slpng.Hb -0.460 -0.402 0.144 -0.362 -0.361 -0.016 -0.189 0.094 0.144
## Pr.Mntl.Hlt -0.336 0.257 -0.061 -0.073 0.099 -0.181 -0.079 0.057 0.315
## Testing_Rat 0.180 -0.085 -0.033 0.016 0.048 -0.111 -0.017 0.001 -0.179
## Hsptlztn_Rt -0.133 -0.222 -0.125 -0.216 -0.040 -0.135 -0.132 -0.117 0.043
## Asthma Hrt.Ds COPD Smokng Diabts N.Ph.A Obesty Pr.S.H Pr.M.H
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises 0.277
## COPD -0.374 -0.561
## Smoking 0.070 0.204 -0.514
## Diabetes -0.123 -0.287 -0.111 0.240
## N.Physcl.Ac 0.012 -0.384 -0.007 -0.333 -0.062
## Obesity -0.272 -0.096 0.164 -0.199 -0.395 -0.062
## Pr.Slpng.Hb 0.073 0.250 -0.206 0.002 -0.013 -0.111 -0.168
## Pr.Mntl.Hlt -0.237 0.087 -0.447 0.087 0.027 0.053 0.096 -0.187
## Testing_Rat -0.359 -0.029 0.174 0.165 0.123 -0.304 0.090 -0.122 -0.089
## Hsptlztn_Rt 0.043 0.090 -0.118 0.095 0.097 -0.040 -0.050 -0.001 -0.038
## Tstn_R
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises
## COPD
## Smoking
## Diabetes
## N.Physcl.Ac
## Obesity
## Pr.Slpng.Hb
## Pr.Mntl.Hlt
## Testing_Rat
## Hsptlztn_Rt 0.259
## fit warnings:
## Some predictor variables are on very different scales: consider rescalingTesting Rate
testing.data.state <- compiled.stats[[length(daily_filenames)]][, c("Province_State", "Testing_Rate")]
testing.data.state <- testing.data.state[!is.na(testing.data.state$Testing_Rate),]
testing.data.state <- testing.data.state[order(testing.data.state$Testing_Rate),]
col.state <- rep("pink", nrow(testing.data.state))
avg.test.rate <- mean(testing.data.state$Testing_Rate, na.rm = T)
col.state[testing.data.state$Testing_Rate < avg.test.rate] <- "grey"
col.state[testing.data.state$Province_State == "Oklahoma"] <- "lightblue"
par(mar = c(5,6,4,2))
barplot(testing.data.state$Testing_Rate, names.arg = testing.data.state$Province_State, horiz = T, main = "Testing Rate by State", las = 2, cex.axis = 1, cex.names = 0.5, col = col.state, border = F, xlab = "Total number of people tested per 100,000 persons.")
abline(v = avg.test.rate, col = "red")
text(x = avg.test.rate + 10, y = 1, labels = "Average Testing Rate", adj = c(0, 0.5), col = "red")
Pink highlights the last 14 days.
day.first.case <- min(which(US.total$cases.total > 100))
n.days <- nrow(US.total)
twoweek.col <- c(rep("grey", n.days-day.first.case-13), rep("pink", 14))
par(mar = c(5,5,4,2))
barplot(US.total$cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 cases by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 cases by Date in US, log scale",
las = 2, cex.axis = 1, cex.names = 0.5, log = "y",
col = twoweek.col, border = F)
barplot(US.total$deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 deaths by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 deaths by Date in US, log scale",
las = 2, cex.axis = 1, cex.names = 0.5, log = "y",
col = twoweek.col, border = F)
barplot(US.total$rise.cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Rise in Cases of COVID-19 by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$rise.deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Rise in Deaths of COVID-19 by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)